Predicting the Risk of Heart Failure With EHR Sequential Data Modeling

• Published in: IEEE access 2018-01, Vol.6, p.9256-9261
• Main Authors: Jin, Bo, Che, Chao, Liu, Zhen, Zhang, Shulong, Yin, Xiaomeng, Wei, Xiaopeng
• Format: Article
• Language: English
• Subjects: Data models; Diagnostic systems; Electronic health records; Heart; Heart failure; Logic gates; Neural networks; Numerical models; Predictive models; risk prediction; Time series analysis; Unstructured data
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2017.2789324

Electronic health records (EHRs) contain patient diagnostic records, physician records, and records of hospital departments. For heart failure, we can obtain mass unstructured data from EHR time series. By analyzing and mining these time-based EHRs, we can identify the links between diagnostic events and ultimately predict when a patient will be diagnosed. However, it is difficult to use the existing EHR data directly, because they are sparse and non-standardized. Thus, this paper proposes an effective and robust architecture for heart failure prediction. The main contribution of this paper is to predict heart failure using a neural network (i.e., to predict the possibility of cardiac illness based on patient's electronic medical data). Specifically, we employed one-hot encoding and word vectors to model the diagnosis events and predicted heart failure events using the basic principles of a long short-term memory network model. Evaluations based on a real-world data set demonstrate the promising utility and efficacy of the proposed architecture in the prediction of the risk of heart failure.